Transformée en scattering sur la spirale temps-chroma-octave
arXiv:1509.00334
Abstract
We introduce a scattering representation for the analysis and classification of sounds. It is locally translation-invariant, stable to deformations in time and frequency, and has the ability to capture harmonic structures. The scattering representation can be interpreted as a convolutional neural network which cascades a wavelet transform in time and along a harmonic spiral. We study its application for the analysis of the deformations of the source-filter model.
in French, 4 pages, 3 figures, presented at GRETSI 2015 in Lyon, France